3D 视觉 - arXivDaily 专题

2403.04755 2024-03-08 cs.CV cs.RO 62%

That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation

Georgi Pramatarov, Matthew Gadd, Paul Newman, Daniele De Martini

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted for publication at the IEEE International Conference on Robotics and Automation (ICRA) 2024

2211.13093 2024-03-07 cs.RO cs.CV 62%

Autonomous Marker-less Rapid Aerial Grasping

Erik Bauer, Barnabas Gavin Cangan, Robert K. Katzschmann

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 8 pages, 10 figures, accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023. Video https://www.youtube.com/watch?v=6hbhAT4l90w

Journal ref 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA, 2023, pp. 6395-6402

2307.13991 2024-03-06 cs.RO cs.CV cs.LG 62%

METAVerse: Meta-Learning Traversability Cost Map for Off-Road Navigation

Junwon Seo, Taekyung Kim, Seongyong Ahn, Kiho Kwak

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Our video can be found at https://youtu.be/4rIAMM1ZKMo

2309.09256 2024-03-05 cs.CV cs.RO 62%

LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models

Kazuto Nakashima, Ryo Kurazume

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments ICRA 2024

2309.13150 2024-03-05 cs.LG cs.CV cs.RO 62%

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations

Hanjiang Hu, Zuxin Liu, Linyi Li, Jiacheng Zhu, Ding Zhao

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Camera-ready version of AISTATS 2024, 30 pages, 5 figures, 13 tables

2402.17264 2024-02-28 cs.CV cs.RO 62%

Explicit Interaction for Fusion-Based Place Recognition

Jingyi Xu, Junyi Ma, Qi Wu, Zijie Zhou, Yue Wang, Xieyuanli Chen, Ling Pei

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

2402.16836 2024-02-27 cs.RO cs.AI cs.CL cs.CV 62%

PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models

Dingkun Guo, Yuqi Xiang, Shuqi Zhao, Xinghao Zhu, Masayoshi Tomizuka, Mingyu Ding, Wei Zhan

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

2402.15464 2024-02-26 cs.RO cs.CV 62%

CLIPPER+: A Fast Maximal Clique Algorithm for Robust Global Registration

Kaveh Fathian, Tyler Summers

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Journal ref IEEE ROBOTICS AND AUTOMATION LETTERS, 2024

2402.09722 2024-02-16 cs.RO cs.AI cs.CV 62%

Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fields

Stephen Hausler, David Hall, Sutharsan Mahendren, Peyman Moghadam

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted to ICRA 2024. The first two authors contributed equally

2402.00467 2024-02-15 cs.RO cs.CV 62%

Can you see me now? Blind spot estimation for autonomous vehicles using scenario-based simulation with random reference sensors

Marc Uecker, J. Marius Zöllner

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

2309.11883 2024-02-15 cs.CV cs.RO 62%

On-the-Fly SfM: What you capture is What you get

Zongqian Zhan, Rui Xia, Yifei Yu, Yibo Xu, Xin Wang

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

2309.15394 2024-02-13 cs.CV cs.RO 62%

KDD-LOAM: Jointly Learned Keypoint Detector and Descriptors Assisted LiDAR Odometry and Mapping

Renlang Huang, Minglei Zhao, Jiming Chen, Liang Li

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

2312.02409 2024-02-07 cs.CV cs.RO 62%

MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR

Yiqian Gan, Hao Xiao, Yizhe Zhao, Ethan Zhang, Zhe Huang, Xin Ye, Lingting Ge

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted to ICRA 2024

2310.10301 2024-02-07 cs.CV cs.RO 62%

Multi-Body Neural Scene Flow

Kavisha Vidanapathirana, Shin-Fang Chng, Xueqian Li, Simon Lucey

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted for 3DV'2024 (oral)

2401.17664 2024-02-01 cs.CV cs.GR 62%

Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation

Yuanhuiyi Lyu, Xu Zheng, Lin Wang

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.GR

2401.16305 2024-01-30 cs.CV cs.RO 62%

MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection

Yuxue Yang, Lue Fan, Zhaoxiang Zhang

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments ICLR 2024, code is available at https://github.com/BraveGroup/PointSAM-for-MixSup

2401.16122 2024-01-30 cs.CV cs.RO 62%

DeFlow: Decoder of Scene Flow Network in Autonomous Driving

Qingwen Zhang, Yi Yang, Heng Fang, Ruoyu Geng, Patric Jensfelt

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 7 pages, 4 figures, Code check https://github.com/KTH-RPL/deflow, accepted by ICRA 2024

2401.10886 2024-01-22 cs.CV cs.AI cs.LG cs.RO 62%

SCENES: Subpixel Correspondence Estimation With Epipolar Supervision

Dominik A. Kloepfer, João F. Henriques, Dylan Campbell

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

2401.10556 2024-01-22 cs.CV cs.GR 62%

Symbol as Points: Panoptic Symbol Spotting via Point-based Representation

Wenlong Liu, Tianyu Yang, Yuhan Wang, Qizhi Yu, Lei Zhang

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.GR

Comments ICLR 2024

2401.09049 2024-01-18 cs.CV cs.RO 62%

Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time

Raphael van Kempen, Tim Rehbronn, Abin Jose, Johannes Stegmaier, Bastian Lampe, Timo Woopen, Lutz Eckstein

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Published as part of the III. International Conference on Electrical, Computer and Energy Technologies (ICECET 2023), Cape Town, South Africa, November 16-17, 2023

2311.03198 2024-01-02 cs.CV cs.RO 62%

LCPR: A Multi-Scale Attention-Based LiDAR-Camera Fusion Network for Place Recognition

Zijie Zhou, Jingyi Xu, Guangming Xiong, Junyi Ma

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted by IEEE Robotics and Automation Letters (RAL) 2023

2312.17260 2024-01-01 cs.CV cs.LG cs.RO 62%

TimePillars: Temporally-Recurrent 3D LiDAR Object Detection

Ernesto Lozano Calvo, Bernardo Taveira, Fredrik Kahl, Niklas Gustafsson, Jonathan Larsson, Adam Tonderski

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 10 pages, 5 figures

2312.11666 2023-12-20 cs.CV cs.GR 62%

HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles

Vanessa Sklyarova, Egor Zakharov, Otmar Hilliges, Michael J. Black, Justus Thies

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.GR

Comments For more results please refer to the project page https://haar.is.tue.mpg.de/

2312.11051 2023-12-19 cs.CV cs.RO 62%

Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object Tracking

Shihao Feng, Pengpeng Liang, Jin Gao, Erkang Cheng

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Preprint version for IEEE Robotics and Automation Letters (RAL)

Journal ref IEEE Robotics and Automation Letters (RAL), vol. 8, no. 12, pp. 8066-8073, 2023

2312.09538 2023-12-18 cs.CV cs.RO 62%

AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition

Yuhang Ming, Jian Ma, Xingrui Yang, Weichen Dai, Yong Peng, Wanzeng Kong

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted by 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)

2309.09314 2023-12-11 cs.GR cs.CV 62%

MOVIN: Real-time Motion Capture using a Single LiDAR

Deok-Kyeong Jang, Dongseok Yang, Deok-Yun Jang, Byeoli Choi, Taeil Jin, Sung-Hee Lee

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.GR

Journal ref Computer Graphics Forum 2023, presented at Pacific Graphics 2023

2312.03345 2023-12-07 cs.RO cs.CV 62%

GraNet: A Multi-Level Graph Network for 6-DoF Grasp Pose Generation in Cluttered Scenes

Haowen Wang, Wanhao Niu, Chungang Zhuang

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments IROS 2023

2312.02208 2023-12-06 cs.CV cs.RO 62%

A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing

Kangcheng Liu

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments International Conference on Robotics and Automation (ICRA) 2022, 6 Figures. arXiv admin note: substantial text overlap with arXiv:2312.01262

2312.01262 2023-12-05 cs.CV cs.RO 62%

A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors

Kangcheng Liu

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments International Journal of Computer Vision (IJCV), 2022. 10 Figures, 13 Tables

2311.17770 2023-11-30 cs.CV cs.RO 62%

PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection

Weixin Mao, Tiancai Wang, Diankun Zhang, Junjie Yan, Osamu Yoshie

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

1. 点云 7719 篇

That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation

Autonomous Marker-less Rapid Aerial Grasping

METAVerse: Meta-Learning Traversability Cost Map for Off-Road Navigation

LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations

Explicit Interaction for Fusion-Based Place Recognition

PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models

CLIPPER+: A Fast Maximal Clique Algorithm for Robust Global Registration

Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fields

Can you see me now? Blind spot estimation for autonomous vehicles using scenario-based simulation with random reference sensors

On-the-Fly SfM: What you capture is What you get

KDD-LOAM: Jointly Learned Keypoint Detector and Descriptors Assisted LiDAR Odometry and Mapping

MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR

Multi-Body Neural Scene Flow

Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation

MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection

DeFlow: Decoder of Scene Flow Network in Autonomous Driving

SCENES: Subpixel Correspondence Estimation With Epipolar Supervision

Symbol as Points: Panoptic Symbol Spotting via Point-based Representation

Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time

LCPR: A Multi-Scale Attention-Based LiDAR-Camera Fusion Network for Place Recognition

TimePillars: Temporally-Recurrent 3D LiDAR Object Detection

HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles

Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object Tracking

AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition

MOVIN: Real-time Motion Capture using a Single LiDAR

GraNet: A Multi-Level Graph Network for 6-DoF Grasp Pose Generation in Cluttered Scenes

A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing

A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors

PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection